gastown

Multi-agent orchestrator for Claude Code. Use when user mentions gastown, gas town, gt commands, bd commands, convoys, polecats, crew, rigs, slinging work, multi-agent coordination, beads, hooks, molecules, workflows, the witness, the mayor, the refinery, the deacon, dogs, escalation, or wants to run multiple AI agents on projects simultaneously. Handles installation, workspace setup, work tracking, agent lifecycle, crash recovery, and all gt/bd CLI operations.

Quality

87%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Medium

Suggest reviewing before use

Quality

Content

70%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body excels at workflow clarity and progressive disclosure, with concrete commands, validation checkpoints, and well-organized real reference files. Its weakness is conciseness: substantial persona/theatrical coaching and ASCII-art flourish examples pad the token budget beyond what the operational content requires.

Suggestions

Trim the 'Creative Freedom' section and its four illustrated flourish examples to a brief bullet list; the persona can be conveyed in a few lines instead of ~50 lines of sample scripts.

Collapse the multiple large ASCII flow diagrams (e.g., the Work Flow box and the Learning example diagram) into a single compact diagram or a short numbered description.

Move extended interaction-style coaching (AskUserQuestion JSON examples, mode signatures) into a reference file, keeping only the core decision rules inline in SKILL.md.

Dimension	Reasoning	Score
Conciseness	Noticeably verbose with several padded sections: extended ASCII-art flow diagrams, a large 'Creative Freedom' persona-coaching block with four illustrated flourish examples, and theatrical voice guidance that does not earn its token cost relative to operational instruction.	2 / 5
Actionability	Mostly executable guidance: a full 'Commands (You Run These)' block and 'System Readiness Checklist' with concrete bash commands; minor gaps where example transcripts use illustrative prose ('slings gt-123 to greenplace') rather than real commands.	4 / 5
Workflow Clarity	Clear sequence with explicit validation and feedback loops: 'System Readiness Checklist' BLOCKERS, a 6-step 'Full Flow Verification', 'Never Assume - Verify Everything' with 'If ANY step fails → investigate and fix', and an 'Error Severity Guide'.	5 / 5
Progressive Disclosure	Clear overview with well-signaled one-level-deep references: a 'Reference Guide' table maps each of 5 real reference files to 'When to Load', plus a grep-based navigation strategy for the large files.	5 / 5
	Total	16 / 20 Passed

Description

100%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is exemplary: it concisely states what the skill does, provides an exhaustive set of natural trigger terms including synonyms and CLI names, and explicitly pairs capabilities with a 'Use when' clause. Third-person voice is maintained throughout.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions: 'Handles installation, workspace setup, work tracking, agent lifecycle, crash recovery, and all gt/bd CLI operations' — comprehensive coverage of specific capabilities.	5 / 5
Completeness	Explicitly answers both: 'Multi-agent orchestrator for Claude Code' (what) and 'Use when user mentions...' with concrete trigger phrases (when).	5 / 5
Trigger Term Quality	Comprehensive natural terms including synonyms and CLI names: 'gastown, gas town, gt commands, bd commands, convoys, polecats, crew, rigs, slinging work, multi-agent coordination, beads, hooks, molecules, workflows'.	5 / 5
Distinctiveness Conflict Risk	Highly specific in-world vocabulary (gastown, polecats, convoys, rigs, beads, witness, mayor, refinery, deacon) anchored to gt/bd CLIs creates a clear niche with minimal conflict risk.	5 / 5
	Total	20 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (705 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: numman-ali/n-skills
Path: skills/tools/gastown/skills/gastown/SKILL.md
Commit: fdabc47

Reviewed: 13 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.